Yunhan Wu's research while affiliated with University College Dublin and other places

Publications (6)

Preprint
Full-text available
Conversational User Interfaces such as Voice Assistants are hugely popular. Yet they are designed to be monolingual by default, lacking support for, or sensitivity to, the bilingual dialogue experience. In this provocation paper, we highlight the language production challenges faced in VA interaction for bilingual users. We argue that, by facilitat...
Preprint
Limited linguistic coverage for Intelligent Personal Assistants (IPAs) means that many interact in a non-native language. Yet we know little about how IPAs currently support or hinder these users. Through native (L1) and non-native (L2) English speakers interacting with Google Assistant on a smartphone and smart speaker, we aim to understand this m...
Preprint
Through proliferation on smartphones and smart speakers, intelligent personal assistants (IPAs) have made speech a common interaction modality. Yet, due to linguistic coverage and varying levels of functionality, many speakers engage with IPAs using a non-native language. This may impact the mental workload and pattern of language production displa...

Citations

... Wu et. al [17] approach this issue with almost the same motivation i.e., to comprehend and analyze the experience of non-native English ASR systems users against those native English systems users. Their quantitative investigation involves assigning 12 basic, day-to-day tasks to 32 users -14 female and 18 males, equally split into native and non-native English speakers and having each participant document their interactions with the Google Assistant agent, accessed either through smartphone and/or smart speaker. ...
... Currently not all languages are supported across speech agents [25], which forces many users to use their L2 rather than their L1 to interact with speech interfaces. Recent research has investigated the challenges L2 speakers face in VA interaction [34,35,41,42]. Some of these works have focused especially on bilingual speakers with an L1 that differs greatly in phonological, lexical and syntactic systems from their L2, such as Mandarin and English [41,42]. ...